2014 playoff notes

To start, a summary of the 2014 regular season data:

This gives us the basis to generate playoff values based on my playoff formula. Playoff Odds are calculated according to this model:

logit P = 0.668 + 0.348*(delta SOS) + 0.434*(delta Playoff Experience)

and the results are:

2014 NFL Playoff Teams, C&F Playoff Model Worksheet.
NFC
Rank	Name	Home Field Advantage	Prev. Playoff Experience	Strength of Schedule	Total Score
1	Seattle Seahawks	0.406	0.434	0.275	1.115
2	Green Bay Packers	0.406	0.434	-0.118	0.722
3	Dallas Cowboys	0.406	0.0	-0.630	-0.224
4	Carolina Panthers	0.406	0.434	-0.292	0.548
5	Arizona Cardinals	0.0	0.0	0.449	0.449
6	Detroit Lions	0.0	0.0	-0.132	-0.132
AFC
1	NE Patriots	0.406	0.434	0.438	1.278
2	Denver Broncos	0.406	0.434	0.550	1.390
3	Pittsburgh Steelers	0.406	0.0	-0.703	-0.297
4	Indianapolis Colts	0.406	0.434	-0.393	0.447
5	Cinncinnati Bengals	0.0	0.434	-0.202	-0.602
6	Baltimore Ravens	0.0	0.0	-0.724	-0.724

 

The total score of a particular team is used as a base. Subtract the score of the opponent and the result is the logit of the win probability for that game. You can use the inverse logit (see Wolfram Alpha to do this easily) to get the probability, and you can multiply the logit of the win probability by 7.4 to get the estimated point spread.

For the second week of the 2014 playoffs, I’ve done all this for you, in the table below. Odds are presented from the home team’s point of view.

Second Round Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	Carolina Panthers	0.567	0.638	4.2
Green Bay Packers	Dallas Cowboys	1.352	0.795	10.0
New England Patriots	Baltimore Ravens	2.002	0.881	14.8
Denver Broncos	Indianapolis Colts	1.349	0.794	10.0

 

Baltimore is not given much of a chance by these techniques, but an interesting analysis by Benjamin Morris of Skeptical Sports (featured now on fivethirtyeight.com) is worth paying attention to. Though the divisional round is hard on teams without a bye, those that survive appear to have a superior chance to go forward in the playoffs. Benjamin has always struck me as an incisive analyst, so he’s absolutely worth paying attention to.

 

On the eve of the Super Bowl: What is the Peyton Manning contribution to Denver’s offense?

The competitors are Denver and Seattle, and as stated previously, my model favors Seattle substantially.

Super Bowl
NFC Champion	AFC Champion	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	Denver Broncos	1.041	0.739	7.7

 

Of course by this point my model has been reduced to a single factor, as there is no home field advantage in the Super Bowl and both teams are playoff experienced. Since every season 8 of the 11 games are before the Conference chanpionships and Super Bowl, the model works best for those first eight games. Still, it’s always interesting to see what the model calculates.

At least as interesting is the Peyton Manning factor, a player having the second best season of his career (as measured by adjusted yards per attempt). I thought it would be interesting to try and figure out how much of the value above average of the potent Denver Broncos attack that Peyton Manning was responsible for. We’ll start by looking at the simple ranking of the team, divided into the offensive and defensive components. Simple rankings help adapt for the quality of opposition, which for Denver was below league average.

Denver Broncos Simple Ranking Stats
Margin of Victory	Strength of Schedule	Simple Ranking	Defensive Simple Ranking	Offensive Simple Ranking
12.47	-1.12	11.35	-3.31	14.65

 

Narrowed down to the essentials, how much of the 14.65 points of Denver offense (above average) was Peyton Manning’s doing? With some pretty simple stats, we can come up with some decent estimates of the Manning contribution to Denver’s value above average.

We’ll start by calculating Peyton’s adjusted yards per attempt, and do so for the league as a whole. We’ll use the Pro Football Reference formula. Later, we’ll use the known conversion factors for AYA to turn that contribution to points, and the subtract the league average from that contribution.

Passing Stats, 2013
Player(s)	Completions	Attempts	Yards	Touchdowns	Interceptions	AYA
Peyton Manning	450	659	5477	55	10	9.3
All NFL passing	11102	18136	120626	804	502	6.3

 

The difference between Peyton Manning’s AYA and the league average is 3 points. Peyton Manning threw 659 times, averaging about 41.2 passes per game. This compares to the average team passing about 35.4 times a game. To convert an AYA into points per 40 passes, the conversion factor is 3.0. This is math people can do in their head. 3 times 3 equals 9 points. In a game situation, in 2013, where Peyton Manning throws 40 passes, he’ll generate 9 points more offense than the average NFL quarterback. So, of the 14.65 points above average that the Denver Broncos generated, Peyton Manning is at least responsible for 61% of that.

Notes:

There is a 0.5 point difference between the AYA reported by Pro Football Reference and the one I calculated for all NFL teams. I suspect PFR came to theirs by taking an average of the AYA of all 32 teams as opposed to calculating the number for all teams. To be sure, we’ll grind the number out step by step.

The yards term: 120626
The TD term: 20 x 804 = 16080
The Int term: 45 x 502 = 22590

120626 + 16080 – 22590 = 114116

Numerator over denominator is:

114116 / 18136 = 6.29223… to two significant digits is 6.3.

 

2014 – 2nd round of NFL Playoffs

My system went 3-0-1 last weekend (Or 3-1 if you consider my prediction in the Bengals – Chargers game a loss, as opposed to “too close to pick”), so time to present playoff odds for the second round of the playoffs.

Divisional Round Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	New Orleans Saints	0.676	0.663	5.0
Carolina Panthers	SF 49ers	-0.157	0.461	-1.2
Denver Broncos	San Diego Chargers	0.411	0.601	3.0
New England Patriots	Indianapolis Colts	-0.060	0.485	-0.4

 

Odds that differ by less than a point in estimated point spread are probably not significant, and from my POV, a suggestion that you don’t bet that particular game.

 

Week 17 stats, and first round NFL Playoff Odds

The regular season has ended and the playoffs have begun. It would be useful to have a set of playoff grade data to do playoff probabilities, and though I’ve been down and out this season (no job at times, foot stress fracture at times, and a bad right shoulder), I currently have some time off my new job, a new laptop, and enough time to grind through some playoff numbers.

NFL stats at the end of the regular season:

To explain the columns above, Median is a median point spread, and can be used to get a feel for how good a team is without overly weighting a blowout win or blowout loss. HS is Brian Burke’s Homemade Sagarin, as implemented in Maggie Xiong’s PDL::Stats. Pred is the predicted Pythagorean expectation. The exponent for this measure is fitted to the data set itself. SOS, SRS, and MOV are the simple ranking components, analyzed via this Perl implementation. MOV is margin of victory, or point spread divided by games played. SOS is strength of schedule. SRS is the simple ranking.

Playoff Odds are calculated according to this model:

logit P  =  0.668 + 0.348*(delta SOS) + 0.434*(delta Playoff Experience)

The results are given below, as a “score” in logits:

2013 NFL Playoff Teams, C&F Playoff Model Worksheet.
NFC
Rank	Name	Home Field Advantage	Prev. Playoff Experience	Strength of Schedule	Total Score
1	Seattle Seahawks	0.406	0.434	0.494	1.334
2	Carolina Panthers	0.406	0.0	0.484	0.889
3	Philadelphia Eagles	0.406	0.0	-0.661	-0.256
4	Green Bay Packers	0.406	0.434	-0.842	-0.003
5	San Francisco 49ers	0.0	0.434	0.612	1.046
6	New Orleans Saints	0.0	0.0	0.658	0.658
AFC
1	Denver Broncos	0.406	0.434	-0.546	0.293
2	NE Patriots	0.406	0.434	-0.258	0.582
3	Cancinnati Bengals	0.406	0.434	-0.856	-0.017
4	Indianapolis Colts	0.406	0.434	0.209	1.048
5	Kansas City Chiefs	0.0	0.0	-0.602	-0.602
6	San Diego Chargers	0.0	0.0	-0.118	-0.118

 

The total score of a particular team is used as a base. Subtract the score of the opponent and the result is the logit of the win probability for that game. You can use the inverse logit (see Wolfram Alpha to do this easily) to get the probability, and you can multiply the logit of the win probability by 7.4 to get the estimated point spread.

For the first week of the playoffs, I’ve done all this for you, in the table below. Odds are presented from the home team’s point of view.

First Round Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Philadelphia Eagles	New Orleans Saints	-0.914	0.286	-6.8
Green Bay Packers	SF 49ers	-1.049	0.259	-7.8
Cincinnati Bengals	San Diego Chargers	0.101	0.525	0.7
Indianapolis Colts	Kansas City Chiefs	1.650	0.839	12.2

 

Some general conclusions from the data above: the teams my model favors most are the Seattle Seahawks, the Indianapolis Colts, the 49ers, the Carolina Panthers, and then the New Orleans Saints, mostly NFC teams. Since the Super Bowl itself does not have a home team, the odds change once you actually reach the Super Bowl. The sum of the SOS column and the Previous Playoff Experience column can be used to estimate odds of winning “the big one”. The strongest team in a Super Bowl setting would be the San Francisco 49ers, with a total score, less HFA, of 1.049. The Indianapolis Colts, with a total score of 0.643 less HFA, would be the strongest possible AFC contender.

A point I’d like the reader to consider is this question: should the New Orleans Saints be granted an exception to the previous playoff experience rule of “last year only counts” and given the 0.434 advantage of a playoff team? 2012 was an aberration as the coach was suspended. I’m not calculating this variation into the formula at this point, but I’ll note that this is an issue that you, the reader, need to resolve for yourself.

The road to the playoffs is not easy, a topic that can be studied by trying to calculate the path to the playoffs of the Indianapolis colts, a team that would be favored in every matchup along the way. Let’s calculate the odds of Indianapolis actually winning all three games.

Odds of Indianapolis reaching the Super Bowl
WP versus Kansas City	WP versus Denver Broncos	WP versus NE Pats	Cume Probability
0.839	0.586	0.515	0.253

 

Three teams from the NFC would be favored over any possible AFC contender. Those are San Francisco, Seattle, and the New Orleans Saints. Carolina would be favored over any AFC contender except the Indianapolis Colts.

 

NFL Season 2013: Week 13

Sorry about any delays in publication. I was between jobs at the time.

Week 13 NFL Stats:

To explain the columns above, Median is a median point spread, and can be used to get a feel for how good a team is without overly weighting a blowout win or blowout loss. HS is Brian Burke’s Homemade Sagarin, as implemented in Maggie Xiong’s PDL::Stats. Pred is the predicted Pythagorean expectation. The exponent for this measure is fitted to the data set itself. SOS, SRS, and MOV are the simple ranking components, analyzed via this Perl implementation. MOV is margin of victory, or point spread divided by games played. SOS is strength of schedule. SRS is the simple ranking.

OSRS and DSRS stats look like this:

The two most impressive teams so far, IMO, are Seattle and Carolina. New Orleans may win the division but right now Carolina is something of a statistical darling.

 

If the playoffs were to be played right now.

If the NFL were to stop playing altogether, and judge teams on their current records, and assign division winners, the playoff rankings in the AFC and NFC would look something like the table below. The teams’ associated playoff stats, according to my playoff model, are also presented.

Playoff Teams, if NFL playoffs were started 10/30/2103.
NFC
Rank	Name	Wins	Losses	Home Field Advantage	Prev. Playoff Experience	Strength of Schedule
1	Seattle Seahawks	7	1	Yes, throughout.	Yes	0.31
2	New Orleans Saints	6	1	Yes, 1 game.	No (?)	-2.28
3	Green Bay Packers	5	2	Yes, 1 game.	Yes	0.30
4	Dallas Cowboys	4	4	Yes, 1 game.	No	0.42
5	San Francisco 49ers	6	2	No	Yes	0.47
6	Detroit Lions	5	3	No	No	0.42
AFC
1	Kansas City Chiefs	8	0	Yes, throughout.	No	-4.34
2	Cinncinnati Bengals	6	2	Yes, 1 game.	Yes	-1.37
3	New England Patriots	6	2	Yes, 1 game.	Yes	-3.06
4	Indianapolis Colts	5	2	Yes, 1 game.	Yes	2.03
5	Denver Broncos	7	1	No	Yes	-2.63
6	San Diego Chargers	4	3	No	No	-2.01

 

The first thing that pops out in this chart is the remarkable strength of schedule advantage Indianapolis has so far. Given their remaining schedule (games with the Texans, Titans, Rams and Jaguars), that advantage is likely to evaporate over the next 8 games, but it leads to the interesting assertion that Indianapolis would be favored by some 14 points over Kansas City should Indianapolis play KC in a second round playoff game, right now.

Kansas City, by contrast, is an exceptionally weak #1 team in terms of playoff experience and strength of schedule. The Chiefs do start playing some tougher teams in the second half, but just a few.

In the NFC, all the possible playoff teams have had about the same strength of schedule except for the Saints, whose schedule has been a lot easier than most. The one factor an analyst will have to decide for themselves is whether the Saints are a team with previous playoff experience, despite the formal definition of the term, in my formula, as experience in last year’s playoffs. I’ve done that in the past, for the 2011 New York Giants.

 

NFL Season 2013: Week 8

Conversation around Atlanta is that the Falcons are effectively out of the playoff hunt, as they would need to go 8-1 to be back in it. Personally, I don’t see how they can become a better team than Carolina at this point, much less New Orleans.

Week 8 NFL Stats:

To explain the columns above, Median is a median point spread, and can be used to get a feel for how good a team is without overly weighting a blowout win or blowout loss. HS is Brian Burke’s Homemade Sagarin, as implemented in Maggie Xiong’s PDL::Stats. Pred is the predicted Pythagorean expectation. The exponent for this measure is fitted to the data set itself. SOS, SRS, and MOV are the simple ranking components, analyzed via this Perl implementation. MOV is margin of victory, or point spread divided by games played. SOS is strength of schedule. SRS is the simple ranking.

OSRS and DSRS stats look like this:

I’m very tempted to start figuring out who would win playoffs if results were frozen and teams were to go into rounds of games at this time. That’s something for a future post, though.